mlsanityData to 7 Oct 2026

Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges

arXiv 2107.02894 ↗First posted 30 Jun 2021cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide application of machine learning techniques -- they are vulnerable to carefully crafted attacks from malicious adversaries. For example, deep neural networks fail to correctly classify adversarial images, which are generated by adding imperceptible perturbations to clean images.We first discuss three main categories of attacks against machine learning techniques -- poisoning attacks, evasion attacks, and privacy attacks. Then the corresponding defense approaches are introduced along with the weakness and limitations of the existing defense approaches. We notice adversarial samples in cybersecurity and computer vision are fundamentally different. While adversarial samples in cybersecurity often have different properties/distributions compared with training data, adversarial images in computer vision are created with minor input perturbations. This further complicates the development of robust learning techniques, because a robust learning technique must withstand different types of attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 58 of its 132 references that are in the map. First posted on arXiv 30 Jun 2021.

Builds on

58 of 132 references.

References · 58

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Deep Learning with Differential Privacycited by 2,682
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
38 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  3. 2016Adversarial Machine Learning at Scalecited by 934
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  7. 2016Universal adversarial perturbationscited by 774
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  12. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  13. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  14. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  15. 2017Countering Adversarial Images using Input Transformationscited by 517
  16. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  17. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  18. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  19. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  20. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  21. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  22. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  23. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  24. 2017Certified Defenses for Data Poisoning Attackscited by 288
  25. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  26. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  27. 2017On Detecting Adversarial Perturbationscited by 232
  28. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  29. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  30. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  31. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  32. 2016Energy-based Generative Adversarial Networkcited by 119
  33. 2018Are adversarial examples inevitable?cited by 113
  34. 2018Adversarial Attacks and Defences Competitioncited by 96
  35. 2018Is feature selection secure against training data poisoning?cited by 88
  36. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  37. 2017DolphinAtack: Inaudible Voice Commandscited by 65
  38. 2017Efficient Defenses Against Adversarial Attackscited by 53

50 most cited of 58 All 58 (JSON)

Built on by

Not cited yet.